☆ 4.7 Article

PDE-constrained models with neural network terms: Optimization and global convergence

JOURNAL OF COMPUTATIONAL PHYSICS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Interdisciplinary Applications

B-PINNs: Bayesian physics-informed neural networks for forward and inverse PDE problems with noisy data

Liu Yang et al.

Summary: The paper introduces a Bayesian physics-informed neural network (B-PINN) for solving nonlinear problems, and conducts experimental comparisons on posterior estimation methods and uncertainty quantification. The KL model is as accurate and faster than BNN, but cannot be applied to high-dimensional problems.

JOURNAL OF COMPUTATIONAL PHYSICS (2021)

添加到收藏夹

Article Engineering, Multidisciplinary

hp-VPINNs: Variational physics-informed neural networks with domain decomposition

Ehsan Kharazmi et al.

Summary: The study proposes a general framework for hp-variational physics-informed neural networks (hp-VPINNs) based on the nonlinear approximation of shallow and deep neural networks and hp-refinement via domain decomposition and projection onto high-order polynomials. The hp-refinement corresponds to a global approximation with a local learning algorithm for efficient network parameter optimization, demonstrating advantages in accuracy and training cost for function approximation and solving differential equations.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

NSFnets (Navier-Stokes flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations

Xiaowei Jin et al.

Summary: In the past 50 years, significant progress has been made in solving Navier-Stokes equations using various numerical methods, but challenges still exist in incorporating multi-fidelity data seamlessly and mesh generation for complex industrial applications. Physics-informed neural networks (PINNs) are employed to directly encode governing equations into deep neural networks, overcoming some limitations for simulating incompressible laminar and turbulent flows. The Navier-Stokes flow nets (NSFnets) are developed using velocity-pressure (VP) and vorticity-velocity (VV) formulations, showing promise in accuracy and convergence rate for benchmark problems as well as turbulent channel flows.

JOURNAL OF COMPUTATIONAL PHYSICS (2021)

添加到收藏夹

Article Mechanics

Flow over an espresso cup: inferring 3-D velocity and pressure fields from tomographic background oriented Schlieren via physics-informed neural networks

Shengze Cai et al.

Summary: This research proposes a new method based on physics-informed neural networks to infer full continuous three-dimensional velocity and pressure fields from Tomo-BOS imaging. Validation on synthetic and real data demonstrates the accuracy and feasibility of the method.

JOURNAL OF FLUID MECHANICS (2021)

添加到收藏夹

Article Thermodynamics

Physics-Informed Neural Networks for Heat Transfer Problems

Shengze Cai et al.

Summary: Physics-informed neural networks (PINNs) have gained popularity in engineering fields for their effectiveness in solving realistic problems with noisy data and partially missing physics. Through automatic differentiation to evaluate differential operators and defining a multitask learning problem, PINNs have been applied to various heat transfer problems, bridging the gap between computational and experimental heat transfer.

JOURNAL OF HEAT TRANSFER-TRANSACTIONS OF THE ASME (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Machine learning-accelerated computational fluid dynamics

Dmitrii Kochkov et al.

Summary: Numerical simulation of fluids is crucial in modeling physical phenomena like weather and aerodynamics, but solving the Navier-Stokes equations at scale remains challenging due to computational costs. This study uses end-to-end deep learning to improve approximations in computational fluid dynamics for modeling two-dimensional turbulent flows, achieving computational speedups and stability while generalizing well to different scenarios. Leveraging machine learning and hardware accelerators, this approach showcases the potential to enhance simulations without sacrificing accuracy or generalization.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2021)

添加到收藏夹

Article Physics, Fluids & Plasmas

Embedded training of neural-network subgrid-scale turbulence models

Jonathan F. MacArt et al.

Summary: In this study, a deep neural-network model is optimized in conjunction with the governing flow equations to provide a model for subgrid-scale stresses in a temporally developing plane turbulent jet at Reynolds number Re-0 = 6000. Training based on this model shows that a lower mesh density is needed for accurate prediction of mean flow, Reynolds stresses, and spectra. However, directly training the neural-network model to match filtered subgrid-scale stresses without incorporating the flow equations during training leads to incorrect predictions.

PHYSICAL REVIEW FLUIDS (2021)

添加到收藏夹

Review Mechanics

Machine Learning for Fluid Mechanics

Steven L. Brunton et al.

ANNUAL REVIEW OF FLUID MECHANICS, VOL 52 (2020)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

DPM: A deep learning PDE augmentation method with application to large-eddy simulation

Justin Sirignano et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2020)

添加到收藏夹

Article Mathematics, Applied

QUANTITATIVE PROPAGATION OF CHAOS IN A BIMOLECULAR CHEMICAL REACTION-DIFFUSION MODEL

Tau Shean Lim et al.

SIAM JOURNAL ON MATHEMATICAL ANALYSIS (2020)

添加到收藏夹

Article Physics, Fluids & Plasmas

Perspective on machine learning for advancing fluid mechanics

M. P. Brenner et al.

PHYSICAL REVIEW FLUIDS (2019)

添加到收藏夹

Article Mechanics

Deep learning of vortex-induced vibrations

Maziar Raissi et al.

JOURNAL OF FLUID MECHANICS (2019)

添加到收藏夹

Article Mechanics

Investigations of data-driven closure for subgrid-scale stress in large-eddy simulation

Zhuo Wang et al.

PHYSICS OF FLUIDS (2018)

添加到收藏夹

Article Mathematics, Applied

Simultaneous single-step one-shot optimization with unsteady PDEs

Stefanie Guenther et al.

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS (2016)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Machine learning strategies for systems with invariance properties

Julia Ling et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2016)

添加到收藏夹

Article Mechanics

Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

Julia Ling et al.

JOURNAL OF FLUID MECHANICS (2016)

添加到收藏夹

Review Thermodynamics

Plasma assisted combustion: Dynamics and chemistry

Yiguang Ju et al.

PROGRESS IN ENERGY AND COMBUSTION SCIENCE (2015)

添加到收藏夹

Article Computer Science, Software Engineering

One-shot methods in function space for PDE-constrained optimal control problems

L. Kaland et al.

OPTIMIZATION METHODS & SOFTWARE (2014)

添加到收藏夹

Article Mathematics, Applied

Adjoint method for a tumor growth PDE-constrained optimization problem

D. A. Knopoff et al.

COMPUTERS & MATHEMATICS WITH APPLICATIONS (2013)

添加到收藏夹

Article Automation & Control Systems

ADJOINT METHODS FOR OBSTACLE PROBLEMS AND WEAKLY COUPLED SYSTEMS OF PDE

Filippo Cagnetti et al.

ESAIM-CONTROL OPTIMISATION AND CALCULUS OF VARIATIONS (2013)

添加到收藏夹

Article Engineering, Aerospace

Continuous Adjoint Approach for the Spalart-Allmaras Model in Aerodynamic Optimization

Alfonso Bueno-Orovio et al.

AIAA JOURNAL (2012)

添加到收藏夹

Review Mechanics

Physics and Computation of Aero-Optics

Meng Wang et al.

ANNUAL REVIEW OF FLUID MECHANICS, VOL 44 (2012)

添加到收藏夹

Article Thermodynamics

Linear eddy mixing based tabulation and artificial neural networks for large eddy simulations of turbulent flames

Baris Ali Sen et al.

COMBUSTION AND FLAME (2010)

添加到收藏夹

Article Thermodynamics

Large eddy simulation of extinction and reignition with artificial neural networks based chemical kinetics

Baris Ali Sen et al.

COMBUSTION AND FLAME (2010)

添加到收藏夹

Article Mathematics, Applied

CONVERGENCE OF LINEARIZED AND ADJOINT APPROXIMATIONS FOR DISCONTINUOUS SOLUTIONS OF CONSERVATION LAWS. PART 2: ADJOINT APPROXIMATIONS AND EXTENSIONS

Mike Giles et al.

SIAM JOURNAL ON NUMERICAL ANALYSIS (2010)

添加到收藏夹

Article Mathematics, Applied

CONVERGENCE OF LINEARIZED AND ADJOINT APPROXIMATIONS FOR DISCONTINUOUS SOLUTIONS OF CONSERVATION LAWS. PART 1: LINEARIZED APPROXIMATIONS AND LINEARIZED OUTPUT FUNCTIONALS

Mike Giles et al.

SIAM JOURNAL ON NUMERICAL ANALYSIS (2010)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Adjoint-based optimization of PDE systems with alternative gradients

Bartosz Protas

JOURNAL OF COMPUTATIONAL PHYSICS (2008)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

High order conservative finite difference scheme for variable density low Mach number turbulent flows

Olivier Desjardins et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2008)

添加到收藏夹

Article Engineering, Aerospace

Direct treatment of state constraints in aerodynamic shape optimization using simultaneous pseudo-time-stepping

Subhendu Bikash Hazra

AIAA JOURNAL (2007)

添加到收藏夹

Article Computer Science, Software Engineering

Simultaneous pseudo-timestepping for PDE-model based optimization problems

SB Hazra et al.

BIT NUMERICAL MATHEMATICS (2004)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

The harmonic adjoint approach to unsteady turbomachinery design

MC Duta et al.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS (2002)

添加到收藏夹

Article Mathematics, Applied

Adjoint recovery of superconvergent functionals from PDE approximations

NA Pierce et al.

SIAM REVIEW (2000)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.